Ioannis Sarridis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ioannis Sarridis has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Symeon Papadopoulos
Information Technologies Institute, CERTH, Thessaloniki, Greece
10 shared publications - Christos Diou
Harokopio University of Athens
4 shared publications - Ioannis Kompatsiaris
Information Technologies Institute, CERTH, Thessaloniki, Greece
4 shared publications - Christos Koutlis
Centre for Research and Technology Hellas Thessaloniki Greece
3 shared publications - Christos Koutlis
Information Technologies Institute @ CERTH
2 shared publications Emmanouil Krasanakis
Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), Thessaloniki, 57001, Greece
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8518-8527
Scaling Vision-Language Models Is Not Enough to Mitigate Bias
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8518-8527
Open AccessScaling Vision-Language Models Is Not Enough to Mitigate Bias
- 8 February 2025
- Published by Springer Nature
- p. 194-208
Towards Fair Face Verification: An In-depth Analysis of Demographic Biases
- 8 February 2025
- Published by Springer Nature
- p. 194-208
Towards Fair Face Verification: An In-depth Analysis of Demographic Biases
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (2) , 1148-1160
FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using such data. However, most of them heavily rely on the availability of protected attribute labels in the dataset, which limits their applicability, while label-unaware approaches, i.e., approaches operating without such labels, exhibit considerably lower performance. To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual information between the features extracted by the model and a protected attribute, without the use of attribute labels. To do that, FLAC proposes a sampling strategy that highlights underrepresented samples in the dataset, and casts the problem of learning fair representations as a probability matching problem that leverages representations extracted by a bias-capturing classifier. It is theoretically shown that FLAC can indeed lead to fair representations, that are independent of the protected attributes. FLAC surpasses the current state-of-the-art on Biased-MNIST, CelebA, and UTKFace, by 29.1%, 18.1%, and 21.9%, respectively. Additionally, FLAC exhibits 2.2% increased accuracy on ImageNet-A and up to 4.2% increased accuracy on Corrupted-Cifar10. Finally, in most experiments, FLAC even outperforms the bias label-aware state-of-the-art methods.
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (2) , 1148-1160
FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using such data. However, most of them heavily rely on the availability of protected attribute labels in the dataset, which limits their applicability, while label-unaware approaches, i.e., approaches operating without such labels, exhibit considerably lower performance. To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual information between the features extracted by the model and a protected attribute, without the use of attribute labels. To do that, FLAC proposes a sampling strategy that highlights underrepresented samples in the dataset, and casts the problem of learning fair representations as a probability matching problem that leverages representations extracted by a bias-capturing classifier. It is theoretically shown that FLAC can indeed lead to fair representations, that are independent of the protected attributes. FLAC surpasses the current state-of-the-art on Biased-MNIST, CelebA, and UTKFace, by 29.1%, 18.1%, and 21.9%, respectively. Additionally, FLAC exhibits 2.2% increased accuracy on ImageNet-A and up to 4.2% increased accuracy on Corrupted-Cifar10. Finally, in most experiments, FLAC even outperforms the bias label-aware state-of-the-art methods.
- Open Access
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 758-766
FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations
EXplainable Artificial Intelligence (XAI) approaches are widely applied for identifying fairness issues in Artificial Intelligence (AI) systems. However, in the context of facial analysis, existing XAI approaches, such as pixel attribution methods, offer explanations for individual images, posing challenges in assessing the overall behavior of a model, which would require labor-intensive manual inspection of a very large number of instances and leaving to the human the task of drawing a general impression of the model behavior from the individual outputs. Addressing this limitation, we introduce FaceX, the first method that provides a comprehensive understanding of face attribute classifiers through summary model explanations. Specifically, FaceX leverages the presence of distinct regions across all facial images to compute a region-level aggregation of model activations, allowing for the visualization of the model's region attribution across 19 predefined regions of interest in facial images, such as hair, ears, or skin. Beyond spatial explanations, FaceX enhances interpretability by visualizing specific image patches with the highest impact on the model's decisions for each facial region within a test benchmark. Through extensive evaluation in various experimental setups, including scenarios with or without intentional biases and mitigation efforts on four benchmarks, namely CelebA, FairFace, CelebAMask-HQ, and Racial Faces in the Wild, FaceX demonstrates high effectiveness in identifying the models' biases.
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 758-766
Open AccessFaceX: Understanding Face Attribute Classifiers through Summary Model Explanations
EXplainable Artificial Intelligence (XAI) approaches are widely applied for identifying fairness issues in Artificial Intelligence (AI) systems. However, in the context of facial analysis, existing XAI approaches, such as pixel attribution methods, offer explanations for individual images, posing challenges in assessing the overall behavior of a model, which would require labor-intensive manual inspection of a very large number of instances and leaving to the human the task of drawing a general impression of the model behavior from the individual outputs. Addressing this limitation, we introduce FaceX, the first method that provides a comprehensive understanding of face attribute classifiers through summary model explanations. Specifically, FaceX leverages the presence of distinct regions across all facial images to compute a region-level aggregation of model activations, allowing for the visualization of the model's region attribution across 19 predefined regions of interest in facial images, such as hair, ears, or skin. Beyond spatial explanations, FaceX enhances interpretability by visualizing specific image patches with the highest impact on the model's decisions for each facial region within a test benchmark. Through extensive evaluation in various experimental setups, including scenarios with or without intentional biases and mitigation efforts on four benchmarks, namely CelebA, FairFace, CelebAMask-HQ, and Racial Faces in the Wild, FaceX demonstrates high effectiveness in identifying the models' biases.
- Open Access
- 18 October 2023
- Published by CERN in Open Research Europe
- Vol. 2, 29
Helios.TALK: A decentralised messaging framework that preserves the privacy of users
Communication via digital means, such as mobile messaging applications (apps), plays an increasingly important role in everyday life. However, most messaging apps employ centralized computing principles that relinquish control of their users’ personal data to social network platform providers. Decentralization has been proposed as an alternative that provides trustworthiness and data confidentiality, but this comes at expense of fewer provided features and non-intuitive user experience. To address this issue, we hereby present two interconnected decentralized messaging tools, developed in the scope of the HELIOS platform, which can support new decentralized social networks. The first tool is a framework that supports the development of context-aware decentralized messaging apps in mobile Android devices by organically tying together many of the platform’s standalone decentralized operations. The second is a decentralized messaging app, called helios.TALK, that builds on the framework but accommodates additional design considerations from the perspective of end-users.
- 18 October 2023
- Published by CERN in Open Research Europe
- Vol. 2, 29
Open AccessHelios.TALK: A decentralised messaging framework that preserves the privacy of users
Communication via digital means, such as mobile messaging applications (apps), plays an increasingly important role in everyday life. However, most messaging apps employ centralized computing principles that relinquish control of their users’ personal data to social network platform providers. Decentralization has been proposed as an alternative that provides trustworthiness and data confidentiality, but this comes at expense of fewer provided features and non-intuitive user experience. To address this issue, we hereby present two interconnected decentralized messaging tools, developed in the scope of the HELIOS platform, which can support new decentralized social networks. The first tool is a framework that supports the development of context-aware decentralized messaging apps in mobile Android devices by organically tying together many of the platform’s standalone decentralized operations. The second is a decentralized messaging app, called helios.TALK, that builds on the framework but accommodates additional design considerations from the perspective of end-users.
- Open Access
Mitigating Viewer Impact from Disturbing Imagery using AI Filters: A User-Study
Exposure to disturbing imagery can significantly impact individuals, especially professionals who encounter such content as part of their work. This paper presents a user study, involving 107 participants, predominantly journalists and human rights investigators, that explores the capability of Artificial Intelligence (AI)-based image filters to potentially mitigate the emotional impact of viewing such disturbing content. We tested five different filter styles, both traditional (Blurring and Partial Blurring) and AI-based (Drawing, Colored Drawing, and Painting), and measured their effectiveness in terms of conveying image information while reducing emotional distress. Our findings suggest that the AI-based Drawing style filter demonstrates the best performance, offering a promising solution for reducing negative feelings (-30.38%) while preserving the interpretability of the image (97.19%). Despite the requirement for many professionals to eventually inspect the original images, participants suggested potential strategies for integrating AI filters into their workflow, such as using AI filters as an initial, preparatory step before viewing the original image. Overall, this paper contributes to the development of a more ethically considerate and effective visual environment for professionals routinely engaging with potentially disturbing imagery.
Open AccessMitigating Viewer Impact from Disturbing Imagery using AI Filters: A User-Study
Exposure to disturbing imagery can significantly impact individuals, especially professionals who encounter such content as part of their work. This paper presents a user study, involving 107 participants, predominantly journalists and human rights investigators, that explores the capability of Artificial Intelligence (AI)-based image filters to potentially mitigate the emotional impact of viewing such disturbing content. We tested five different filter styles, both traditional (Blurring and Partial Blurring) and AI-based (Drawing, Colored Drawing, and Painting), and measured their effectiveness in terms of conveying image information while reducing emotional distress. Our findings suggest that the AI-based Drawing style filter demonstrates the best performance, offering a promising solution for reducing negative feelings (-30.38%) while preserving the interpretability of the image (97.19%). Despite the requirement for many professionals to eventually inspect the original images, participants suggested potential strategies for integrating AI filters into their workflow, such as using AI filters as an initial, preparatory step before viewing the original image. Overall, this paper contributes to the development of a more ethically considerate and effective visual environment for professionals routinely engaging with potentially disturbing imagery.
- Open Access
Towards Fair Face Verification: An In-depth Analysis of Demographic Biases
Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cloud-based solutions, have been found to exhibit significant biases related to race, age, and gender, a problem that requires in-depth exploration and solutions. This paper presents an in-depth analysis, with a particular emphasis on the intersectionality of these demographic factors. Intersectional bias refers to the performance discrepancies w.r.t. the different combinations of race, age, and gender groups, an area relatively unexplored in current literature. Furthermore, the reliance of most state-of-the-art approaches on accuracy as the principal evaluation metric often masks significant demographic disparities in performance. To counter this crucial limitation, we incorporate five additional metrics in our quantitative analysis, including disparate impact and mistreatment metrics, which are typically ignored by the relevant fairness-aware approaches. Results on the Racial Faces in-the-Wild (RFW) benchmark indicate pervasive biases in face recognition systems, extending beyond race, with different demographic factors yielding significantly disparate outcomes. In particular, Africans demonstrate an 11.25% lower True Positive Rate (TPR) compared to Caucasians, while only a 3.51% accuracy drop is observed. Even more concerning, the intersections of multiple protected groups, such as African females over 60 years old, demonstrate a +39.89% disparate mistreatment rate compared to the highest Caucasians rate. By shedding light on these biases and their implications, this paper aims to stimulate further research towards developing fairer, more equitable face recognition and verification systems.
Open AccessTowards Fair Face Verification: An In-depth Analysis of Demographic Biases
Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cloud-based solutions, have been found to exhibit significant biases related to race, age, and gender, a problem that requires in-depth exploration and solutions. This paper presents an in-depth analysis, with a particular emphasis on the intersectionality of these demographic factors. Intersectional bias refers to the performance discrepancies w.r.t. the different combinations of race, age, and gender groups, an area relatively unexplored in current literature. Furthermore, the reliance of most state-of-the-art approaches on accuracy as the principal evaluation metric often masks significant demographic disparities in performance. To counter this crucial limitation, we incorporate five additional metrics in our quantitative analysis, including disparate impact and mistreatment metrics, which are typically ignored by the relevant fairness-aware approaches. Results on the Racial Faces in-the-Wild (RFW) benchmark indicate pervasive biases in face recognition systems, extending beyond race, with different demographic factors yielding significantly disparate outcomes. In particular, Africans demonstrate an 11.25% lower True Positive Rate (TPR) compared to Caucasians, while only a 3.51% accuracy drop is observed. Even more concerning, the intersections of multiple protected groups, such as African females over 60 years old, demonstrate a +39.89% disparate mistreatment rate compared to the highest Caucasians rate. By shedding light on these biases and their implications, this paper aims to stimulate further research towards developing fairer, more equitable face recognition and verification systems.
- Open Access
InDistill: Information flow-preserving knowledge distillation for model compression
In this paper we introduce InDistill, a model compression approach that combines knowledge distillation and channel pruning in a unified framework for the transfer of the critical information flow paths from a heavyweight teacher to a lightweight student. Such information is typically collapsed in previous methods due to an encoding stage prior to distillation. By contrast, InDistill leverages a pruning operation applied to the teacher's intermediate layers reducing their width to the corresponding student layers' width. In that way, we force architectural alignment enabling the intermediate layers to be directly distilled without the need of an encoding stage. Additionally, a curriculum learning-based training scheme is adopted considering the distillation difficulty of each layer and the critical learning periods in which the information flow paths are created. The proposed method surpasses state-of-the-art performance on three standard benchmarks, i.e. CIFAR-10, CUB-200, and FashionMNIST by 3.08%, 14.27%, and 1% mAP, respectively, as well as on more challenging evaluation settings, i.e. ImageNet and CIFAR-100 by 1.97% and 5.65% mAP, respectively.
Open AccessInDistill: Information flow-preserving knowledge distillation for model compression
In this paper we introduce InDistill, a model compression approach that combines knowledge distillation and channel pruning in a unified framework for the transfer of the critical information flow paths from a heavyweight teacher to a lightweight student. Such information is typically collapsed in previous methods due to an encoding stage prior to distillation. By contrast, InDistill leverages a pruning operation applied to the teacher's intermediate layers reducing their width to the corresponding student layers' width. In that way, we force architectural alignment enabling the intermediate layers to be directly distilled without the need of an encoding stage. Additionally, a curriculum learning-based training scheme is adopted considering the distillation difficulty of each layer and the critical learning periods in which the information flow paths are created. The proposed method surpasses state-of-the-art performance on three standard benchmarks, i.e. CIFAR-10, CUB-200, and FashionMNIST by 3.08%, 14.27%, and 1% mAP, respectively, as well as on more challenging evaluation settings, i.e. ImageNet and CIFAR-100 by 1.97% and 5.65% mAP, respectively.
- Open Access
Leveraging Large-scale Multimedia Datasets to Refine Content Moderation Models
The sheer volume of online user-generated content has rendered content moderation technologies essential in order to protect digital platform audiences from content that may cause anxiety, worry, or concern. Despite the efforts towards developing automated solutions to tackle this problem, creating accurate models remains challenging due to the lack of adequate task-specific training data. The fact that manually annotating such data is a highly demanding procedure that could severely affect the annotators' emotional well-being is directly related to the latter limitation. In this paper, we propose the CM-Refinery framework that leverages large-scale multimedia datasets to automatically extend initial training datasets with hard examples that can refine content moderation models, while significantly reducing the involvement of human annotators. We apply our method on two model adaptation strategies designed with respect to the different challenges observed while collecting data, i.e. lack of (i) task-specific negative data or (ii) both positive and negative data. Additionally, we introduce a diversity criterion applied to the data collection process that further enhances the generalization performance of the refined models. The proposed method is evaluated on the Not Safe for Work (NSFW) and disturbing content detection tasks on benchmark datasets achieving 1.32% and 1.94% accuracy improvements compared to the state of the art, respectively. Finally, it significantly reduces human involvement, as 92.54% of data are automatically annotated in case of disturbing content while no human intervention is required for the NSFW task.
Open AccessLeveraging Large-scale Multimedia Datasets to Refine Content Moderation Models
The sheer volume of online user-generated content has rendered content moderation technologies essential in order to protect digital platform audiences from content that may cause anxiety, worry, or concern. Despite the efforts towards developing automated solutions to tackle this problem, creating accurate models remains challenging due to the lack of adequate task-specific training data. The fact that manually annotating such data is a highly demanding procedure that could severely affect the annotators' emotional well-being is directly related to the latter limitation. In this paper, we propose the CM-Refinery framework that leverages large-scale multimedia datasets to automatically extend initial training datasets with hard examples that can refine content moderation models, while significantly reducing the involvement of human annotators. We apply our method on two model adaptation strategies designed with respect to the different challenges observed while collecting data, i.e. lack of (i) task-specific negative data or (ii) both positive and negative data. Additionally, we introduce a diversity criterion applied to the data collection process that further enhances the generalization performance of the refined models. The proposed method is evaluated on the Not Safe for Work (NSFW) and disturbing content detection tasks on benchmark datasets achieving 1.32% and 1.94% accuracy improvements compared to the state of the art, respectively. Finally, it significantly reduces human involvement, as 92.54% of data are automatically annotated in case of disturbing content while no human intervention is required for the NSFW task.
- 28 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (2) , 724-735
An Autoregressive Graph Convolutional Long Short-Term Memory Hybrid Neural Network for Accurate Prediction of COVID-19 Cases
Efficient prediction of COVID-19 cases could prepare the healthcare system to accommodate the COVID-19 cases in the forthcoming days and improve the overall resource management. A hybrid model comprised of an autoregressive filter, a graph convolutional neural network (GCN), and a long short-term memory neural network is proposed for COVID-19 cases prediction in USA. It captures accurately both linearities and nonlinearities present in the time series. An adjacency matrix is exploited in GCN that relies on Granger causality tests applied to historical COVID-19 cases for each state in USA. By doing so, the latent information about the spread of the virus is captured efficiently and the prediction performance of the hybrid model is improved, revealing which state truly affects the other ones. The proposed method outperforms the state-of-the-art techniques.
- 28 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (2) , 724-735
An Autoregressive Graph Convolutional Long Short-Term Memory Hybrid Neural Network for Accurate Prediction of COVID-19 Cases
Efficient prediction of COVID-19 cases could prepare the healthcare system to accommodate the COVID-19 cases in the forthcoming days and improve the overall resource management. A hybrid model comprised of an autoregressive filter, a graph convolutional neural network (GCN), and a long short-term memory neural network is proposed for COVID-19 cases prediction in USA. It captures accurately both linearities and nonlinearities present in the time series. An adjacency matrix is exploited in GCN that relies on Granger causality tests applied to historical COVID-19 cases for each state in USA. By doing so, the latent information about the spread of the virus is captured efficiently and the prediction performance of the hybrid model is improved, revealing which state truly affects the other ones. The proposed method outperforms the state-of-the-art techniques.